· 9 min read
Access Control
Multi Tenant RAG: Enforce Access Control Before Retrieval
A reference architecture for tenant isolation, document ACLs, permission revocation, and authorization tests in RAG systems.
Read moreIDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
11 articles
· 9 min read
Access Control
A reference architecture for tenant isolation, document ACLs, permission revocation, and authorization tests in RAG systems.
Read more· 5 min read
architecture
Embed 5 Pro and Fast share one vector space: index once with Pro, query with either model, lose 1.6-2.7% retrieval quality and gain 2.4x query throughput. Here's the actual math for when that trade is worth making.
Read more· 5 min read
ai
Qdrant released a 10-billion-document benchmark dataset on September 1, 2026, built from over a quadrillion brute-force distance calculations. I ran our production filter patterns against the old 1M-vector benchmark we'd been trusting. The gap explains a slowdown we never diagnosed.
Read more· 15 min read
agent-learning
Part 10 of 12 — Make agents smarter over time with long-term memory, RAG, task reflection, and inter-agent knowledge sharing.
Read more· 12 min read
agentic-ai
A complete technical guide to building a profitable agentic AI system using only open-source tools — with retrieval, orchestration, tool use, and observability. Includes architecture diagrams and real cost analysis.
Read more· 19 min read
agentic-ai
Complete hands-on guide to building a production-ready agentic AI system. From project setup to deployment — every layer implemented with working code, tests, and Docker compose.
Read more· 6 min read
2026
When everyone uses AI/Agents, models become a commodity. That's when Data becomes the real differentiator — deciding whether your agent runs 'for fun' or 'accurately, optimally, and consistently'. AI Skills and Data Skills are an inseparable duo.
Read more· 13 min read
ai
What is AI hallucination? Why does AI invent facts? Learn detailed strategies for minimizing hallucinations in Claude, Gemini, Copilot, and Cursor — from prompt engineering to RAG, grounding, and verification loops.
Read more· 21 min read
ai
Part 6 of 12 — Your voice interviewer is only as good as what it knows. Here's how to build a real-time RAG system that retrieves rubrics, job descriptions, and technical knowledge in under 50ms.
Read moreLooking for an article, exploring a product, or starting an AI project?